Variational Autoencoder with Normalizing flow for X-ray spectral fitting
This work addresses a domain-specific problem for astrophysicists studying black hole accretion, offering a significant speed-up over existing methods.
The paper tackled the computational inefficiency of traditional spectral fitting methods like MCMC for black hole X-ray binaries by introducing a variational autoencoder with normalizing flow, achieving three orders of magnitude faster performance while improving spectral reconstructions.
Black hole X-ray binaries (BHBs) can be studied with spectral fitting to provide physical constraints on accretion in extreme gravitational environments. Traditional methods of spectral fitting such as Markov Chain Monte Carlo (MCMC) face limitations due to computational times. We introduce a probabilistic model, utilizing a variational autoencoder with a normalizing flow, trained to adopt a physical latent space. This neural network produces predictions for spectral-model parameters as well as their full probability distributions. Our implementations result in a significant improvement in spectral reconstructions over a previous deterministic model while performing three orders of magnitude faster than traditional methods.